arXiv:2512.17505v1 Announce Type: cross 
Abstract: This study presents an innovative hybrid Visual-Inertial Odometry (VIO) method for Unmanned Aerial Vehicles (UAVs) that is resilient to environmental challenges and capable of dynamically assessing sensor reliability. Built upon a loosely coupled sensor fusion architecture, the system utilizes a novel hybrid Quaternion-focused Error-State EKF/UKF (Qf-ES-EKF/UKF) architecture to process inertial measurement unit (IMU) data. This architecture first propagates the entire state using an Error-State Extended Kalman Filter (ESKF) and then applies a targeted Scaled Unscented Kalman Filter (SUKF) step to refine only the orientation. This sequential process blends the accuracy of SUKF in quaternion estimation with the overall computational efficiency of ESKF. The reliability of visual measurements is assessed via a dynamic sensor confidence score based on metrics, such as image entropy, intensity variation, motion blur, and inference quality, adapting the measurement noise covariance to ensure stable pose estimation even under challenging conditions. Comprehensive experimental analyses on the EuRoC MAV dataset demonstrate key advantages: an average improvement of 49% in position accuracy in challenging scenarios, an average of 57% in rotation accuracy over ESKF-based methods, and SUKF-comparable accuracy achieved with approximately 48% lower computational cost than a full SUKF implementation. These findings demonstrate that the presented approach strikes an effective balance between computational efficiency and estimation accuracy, and significantly enhances UAV pose estimation performance in complex environments with varying sensor reliability.

تم تقديم طريقة هجينة جديدة لتحديد المواقع البصرية والحركية (VIO) للطائرات بدون طيار (UAV)، تستخدم بنية مبتكرة تعتمد على مرشح كالمان الممتد (EKF) ومرشح كالمان غير الخطي (UKF) المركّز على الكواتيرنيونات. يقوم هذا النظام بتقييم موثوقية المستشعرات ديناميكيًا ومعالجة بيانات وحدة القياس الحركية، مما يعزز الأداء في البيئات الصعبة.

Se ha introducido un nuevo método híbrido de Odometría Visual-Inercial (VIO) para Vehículos Aéreos No Tripulados (UAV), que utiliza una innovadora arquitectura de EKF/UKF centrada en cuaterniones. Este sistema evalúa dinámicamente la fiabilidad de los sensores y procesa los datos de la unidad de medida inercial, mejorando el rendimiento en entornos desafiantes.

Une nouvelle méthode hybride d'odométrie visuelle-inertielle (VIO) a été introduite pour les véhicules aériens sans pilote (UAV), utilisant une architecture innovante d'EKF/UKF axée sur les quaternions. Ce système évalue dynamiquement la fiabilité des capteurs et traite les données des unités de mesure inertielle, améliorant ainsi les performances dans des environnements difficiles.

A new hybrid Visual-Inertial Odometry (VIO) method has been introduced for Unmanned Aerial Vehicles (UAVs), utilizing an innovative Quaternion-focused Error-State EKF/UKF architecture. This system dynamically assesses sensor reliability and processes inertial measurement unit data, enhancing performance in challenging environments.

Adaptive Covariance and Quaternion-Focused Hybrid Error-State EKF/UKF for Visual-Inertial Odometry

Was this article worth reading? Share it

LucidQuery AI

Vermeer

Attentive AI

LangWatch

Octofy

Dyad

Ready to build your own newsroom?